From d2a2d006a41a8f1f94c8cc45de9068838916e32a Mon Sep 17 00:00:00 2001
From: Christian Jeworrek <christian.jeworrek@its-jeworrek.de>
Date: Wed, 26 Feb 2025 19:41:38 +0100
Subject: [PATCH] syntax, timezone

---
 scripts/einsaetze_rss_feed.py | 33 ++++++++++++++++++++-------------
 1 file changed, 20 insertions(+), 13 deletions(-)

diff --git a/scripts/einsaetze_rss_feed.py b/scripts/einsaetze_rss_feed.py
index 76d7c73..dbee5e4 100644
--- a/scripts/einsaetze_rss_feed.py
+++ b/scripts/einsaetze_rss_feed.py
@@ -1,34 +1,41 @@
 #!/bin/python3
 import re
+import locale
+from datetime import datetime
+from pytz import timezone
 import requests
 from bs4 import BeautifulSoup
-from datetime import datetime
-import locale
 locale.setlocale(locale.LC_TIME, 'de_DE.UTF-8')
 
-soup = BeautifulSoup(requests.get("https://www.feuerwehr-nea.de/einsaetze/").content, 'html.parser')
+BASEURL = "https://www.feuerwehr-nea.de"
+FWNAME = "Feuerwehr Nea"
+
+soup = BeautifulSoup(requests.get(BASEURL + "/einsaetze",timeout=20).content, 'html.parser')
 
 print('<?xml version="1.0" encoding="UTF-8" ?>\n'
 '<rss version="2.0">'
 '<channel>'
-'<title>feuerwehr-nea.de Eins&auml;tze</title>'
-'<link>https://www.feuerwehr-nea.de/einsaetze/</link>'
-'<description>feuerwehr-nea.de Eins&auml;tze</description>')
+'<title>' + FWNAME +' Einsätze</title>'
+'<link>' + BASEURL + '</link>'
+'<description>' + FWNAME + ' Einsätze</description>')
 
 for mysoup in soup.find_all('article', class_='teaser-element'):
     mydatetime_str = mysoup.find('span', class_="date").string
     mydatetime = datetime.strptime(mydatetime_str, '%d. %B  %Y %H:%M')
-    mylink = "https://www.feuerwehr-nea.de" + (mysoup.find('a', class_="einsatz-link"))['href']
-    soup2 = BeautifulSoup(requests.get(mylink).content, 'html.parser')
+    mydatetime = timezone("CET").localize(mydatetime)
+    mylink = BASEURL + (mysoup.find('a', class_="einsatz-link"))['href']
+    soup2 = BeautifulSoup(requests.get(mylink,timeout=10).content, 'html.parser')
     mylist = []
+    mykeywords = myunits = ""
     for itemsoup in (soup2.find('tbody').find_all('td')):
-      mylist.append(re.sub(r"\n\ *", "", itemsoup.string.strip()))
-    if(len(mylist) >= 4):
-      mykeywords = mylist[3]
-      myunits = mylist[2]
+        mylist.append(re.sub(r"\n\ *", " ", itemsoup.string.strip()))
+    if len(mylist) >= 4:
+        mykeywords = mylist[3]
+    if len(mylist) >= 3:
+        myunits = mylist[2]
     print("<item>")
     locale.setlocale(locale.LC_TIME, 'en_US.UTF-8')
-    print("<pubDate>" + mydatetime.strftime('%a, %d %b %Y %H:%M:%S +0100') + "</pubDate>")
+    print("<pubDate>" + mydatetime.strftime('%a, %d %b %Y %H:%M:%S %z') + "</pubDate>")
     locale.setlocale(locale.LC_TIME, 'de_DE.UTF-8')
     print("<title>" + mykeywords + " - " + (mysoup.find('h3', class_="heading")).string.strip() + " - " + myunits +  "</title>")
     print("<link>" + mylink + "</link>")